BSEM MI analysis for categorical data PreviousNext
Mplus Discussion > Categorical Data Modeling >
Message/Author
 Shanshan Wang posted on Thursday, January 21, 2016 - 9:26 am
Hi Mplus veterans,

I want to use Bayesian method to test full measurement invaraince (scalar MI) for categorical data. There are 8 items in 30 different groups. I fixed the factor variance at 1 for all groups. Also, I fixed the factor mean at 0 for the reference group (%c#1%).

Is my method correct? Any comments are greatly appreciated.

Thank you in advance!
SW

VARIABLE:
NAMES = id group y1-y8;
USEVARIABLES = group y1-y8;
CATEGORICAL = y1-y8;
CLASSES = c(30);
KNOWNCLASS = c(group = 1-30);
ANALYSIS:
ESTIMATOR = BAYES;
PROCESSORS = 2;
BSEED = 48932;
BCONVERGENCE = .05;
TYPE = MIXTURE;
Biterations = 50000000(1000);
MODEL:
%OVERALL%
f by y1*y2-y8;
!factor variance is fixed at 1 for all groups.
f@1;
%c#1%
!factor mean is fixed at 0 for the reference group.
[f@0];
OUTPUT:
TECH1 TECH8;
 Bengt O. Muthen posted on Thursday, January 21, 2016 - 4:19 pm
I would fix the factor variance to 1 in only one group.
Back to top
Add Your Message Here
Post:
Username: Posting Information:
This is a private posting area. Only registered users and moderators may post messages here.
Password:
Options: Enable HTML code in message
Automatically activate URLs in message
Action: